ghcp-cli-dashboard 0.7.1

A local web dashboard that monitors all your GitHub Copilot CLI sessions in real-time

Copilot Session Dashboard

A local web dashboard that monitors all your GitHub Copilot CLI and Claude Code sessions in real-time. Designed for power users running multiple AI coding sessions simultaneously.

[!TIP] The dashboard works out of the box by reading events.jsonl files from your Copilot session directories. For richer session history (summaries, checkpoints), enable the SESSION_STORE experimental feature: add "experimental": true to ~/.copilot/config.json and start a new Copilot session.

Installation

Option 1: From PyPI

pip install ghcp-cli-dashboard

Option 2: From Source

# Clone the repo
git clone https://github.com/JeffSteinbok/ghcpCliDashboard.git
cd ghcpCliDashboard

# Install in editable mode
pip install -e .

Usage

# Start the dashboard
copilot-dashboard start

# Start in background
copilot-dashboard start --background

# Check status
copilot-dashboard status

# Stop
copilot-dashboard stop

Open http://localhost:5111 in your browser.

Features

Session States

• Working / Thinking (green) — session is actively running tools or reasoning
• Waiting (yellow) — session needs your input (ask_user or ask_permission pending)
• Idle (blue) — session is done and ready for your next task

Desktop Notifications

Click the 🔕 button in the header to enable browser notifications. You'll get an alert whenever a session transitions from working to waiting or idle, so you can stay on top of sessions that need attention without watching the dashboard.

Views

• Tile view (default) — compact card grid to see all sessions at a glance
• List view — detailed expandable rows with full session info
• Toggle between views with the buttons next to the Active/Previous tabs

Session Monitoring

• Active vs Previous — sessions with a running copilot.exe or claude.exe process appear in the Active tab
• Claude Code support — automatically discovers Claude Code sessions from ~/.claude/projects/, including active sessions not yet indexed. Claude sessions display a ✦ Claude badge.
• Waiting context — when a session is waiting, shows what it's asking (e.g. the ask_user question and choices)
• Background tasks — shows count of running subagents per session
• YOLO mode indicator — shows 🔥 YOLO badge for sessions running with --yolo
• MCP servers — displays connected MCP servers (e.g. bluebird, icm, github) for both active and past sessions
• Project grouping — sessions are auto-categorized by repo, working directory, or content analysis

Actions

• Focus window — click 📺 on an active session to bring its terminal window to the foreground
• Restart commands — each session has a copy-pasteable copilot --resume <id> command (includes --yolo only if the session was running with it)
• Session details — click any session to see checkpoints, recent tool output, references, and conversation history

Appearance

• Light/Dark mode toggle
• 9 color palettes — Default, Pink, Ocean, Forest, Sunset, Mono, Neon, Slate, and Rose Gold
• Auto-refresh — active sessions poll every 5s, full session list every 30s; expanded sections and collapsed groups persist across refreshes

Cross-Machine Sync

See active sessions from all your machines in one dashboard — powered by OneDrive, Google Drive, or any cloud-synced folder. No Git commits needed.

How it works:

• On each poll cycle, the dashboard exports your active sessions as JSON files to a shared cloud folder
• Other machines read those files and display them in a "Remote Sessions" section under Active
• Each machine only writes to its own subfolder — no sync conflicts

Auto-detection (priority order):

1. OneDriveCommercial (preferred — prevents data leakage to personal accounts)
2. OneDriveConsumer
3. User Documents folder

Configuration (~/.copilot/dashboard-config.json):

{
  "sync": {
    "enabled": true,
    "folder": "D:\\MyCloudSync"
  }
}

• Set "enabled": false to disable sync entirely
• Set "folder" to override auto-detection with a specific path

What remote sessions show:

• Live state indicators (working, waiting, idle)
• Session summary, intent, branch, MCP servers, turn/checkpoint counts
• Machine name badge (e.g. 🖥️ LAPTOP-HOME)

What remote sessions don't show:

• No detail drill-down (checkpoints, turns, files)
• No focus or kill actions (those are local-only)
• No past/previous sessions from remote machines

Prerequisites

Package	Purpose
fastapi	Web framework with auto-generated OpenAPI docs
uvicorn	ASGI server
pywin32	Window focus and process detection (Windows-only)

Both are installed automatically via pip install ghcp-cli-dashboard.

For more details on architecture, data sources, and API endpoints, see DEVELOPMENT.md.